Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 281
    Prev
    Next
    INDEX
    Explanations

    comparisons and expressions of opinions using the word "like."

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinion or judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    milo
    -0.78
    "]=>
    -0.78
    */(
    -0.73
     secondly
    -0.69
    bara
    -0.68
    ounty
    -0.67
    ARS
    -0.67
    conservancy
    -0.67
    encers
    -0.66
     ashore
    -0.66
    POSITIVE LOGITS
     innocuous
    0.92
     reasonable
    0.88
     distant
    0.86
     contradiction
    0.84
     logical
    0.82
     quaint
    0.81
    brainer
    0.81
     sensible
    0.79
     oxy
    0.78
     harmless
    0.78
    Activations Density 0.144%

    No Known Activations